skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

1.87x

Quality

85%

Does it follow best practices?

Impact

88%

1.87x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

86%

Setting Up Evaluation Infrastructure for a New Skill

Eval workspace structure and metadata

Criteria

Without context

With context

Workspace naming

100%

Iteration subdirectory

100%

Descriptive eval names

58%

100%

eval_metadata.json presence

100%

eval_metadata eval_name field

100%

eval_metadata required fields

25%

100%

evals.json location and schema

40%

100%

evals.json entry fields

100%

No-skill baseline structure

100%

Simultaneous run launch plan

100%

88%

20%

Create a Skill for Automated Git Commit Message Generation

Skill authoring style and structure

Criteria

Without context

With context

Pushy trigger language

100%

Trigger contexts in description

100%

SKILL.md line count

100%

Imperative instructions

100%

WHY reasoning present

100%

No bare all-caps commands

100%

Valid YAML frontmatter

100%

evals.json skill_name and array

50%

100%

evals.json entry fields

50%

100%

No assertions in initial evals

100%

94%

12%

Improve Skill Triggering Accuracy with Eval Queries

Trigger eval query generation

Criteria

Without context

With context

Exactly 20 queries

100%

Correct JSON structure

100%

Sufficient should-trigger queries

100%

Sufficient should-not-trigger queries

100%

Specific should-trigger queries

100%

Near-miss should-not-trigger queries

100%

No obviously irrelevant queries

100%

Varied should-trigger phrasings

100%

Casual or informal queries

62%

100%

Query length variety

50%

40%

Repository: boisenoise/skills-collections
Commit: 636b862

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Setting Up Evaluation Infrastructure for a New Skill Create a Skill for Automated Git Commit Message Generation Improve Skill Triggering Accuracy with Eval Queries

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.